CN110442099B - Numerical control machining process parameter optimization method based on long-term and short-term memory - Google Patents

Numerical control machining process parameter optimization method based on long-term and short-term memory Download PDF

Info

Publication number
CN110442099B
CN110442099B CN201910716189.7A CN201910716189A CN110442099B CN 110442099 B CN110442099 B CN 110442099B CN 201910716189 A CN201910716189 A CN 201910716189A CN 110442099 B CN110442099 B CN 110442099B
Authority
CN
China
Prior art keywords
feeding speed
speed
numerical control
code
long
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910716189.7A
Other languages
Chinese (zh)
Other versions
CN110442099A (en
Inventor
吴继春
方海国
阳广兴
罗涛
胡裕栋
周会成
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiangtan University
Original Assignee
Xiangtan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Xiangtan University filed Critical Xiangtan University
Priority to CN201910716189.7A priority Critical patent/CN110442099B/en
Publication of CN110442099A publication Critical patent/CN110442099A/en
Application granted granted Critical
Publication of CN110442099B publication Critical patent/CN110442099B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/30—Nc systems
    • G05B2219/32—Operator till task planning
    • G05B2219/32252—Scheduling production, machining, job shop
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
    • Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Manufacturing & Machinery (AREA)
  • Quality & Reliability (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Numerical Control (AREA)

Abstract

The embodiment of the invention discloses a numerical control machining process parameter optimization method based on long-term and short-term memory, which comprises the following steps of S1, operating a G code to obtain an instruction serial number of the G code, and working task data and state data including a feeding speed; step S2, the deep neural network forwards propagates and predicts the feeding speed of the nth time of the G code of the mth line of the next state of the current state according to the received state data of the current state
Figure DDA0002155507390000011
Step S3, judging the feeding speed
Figure DDA0002155507390000012
Whether the speed is within the allowable range of the feed speed, if so, the step S4 is performed, otherwise, the step S2 is returned to; step S4, use
Figure DDA0002155507390000013
Carrying out nth replacement correction on the feeding speed of the G code of the original mth line, and operating; step S5, judging whether the machining precision ERR and the machining efficiency are larger than preset values, if so, executing step S6, otherwise, returning to step S2, step S6, judging whether the parameters are finished, if so, turning to step S7, otherwise, returning to step S1; and step S7, extracting the optimal parameters.

Description

Numerical control machining process parameter optimization method based on long-term and short-term memory
Technical Field
The embodiment of the invention relates to the technical field of machining process parameter optimization, in particular to a numerical control machining process parameter optimization method based on long-term and short-term memory.
Background
In the machining process, machining precision and machining efficiency are closely related to cutting parameters, although a machining path can be generated through CAM software, the setting of the technological parameters is usually dependent on experience values of workers, the specific values of the technological parameters cannot be exerted to the maximum extent, the increase of cutting force is often caused by improper parameter setting, and finally the service lives of a cutter and a machine tool are even influenced.
The existing processing methods reduce time by modifying the geometrical characteristics of a free cutting feed section, the retreating of a cutter and the like, and the methods cannot optimize the feeding speed related to the processing efficiency.
Disclosure of Invention
Therefore, the embodiment of the invention provides a numerical control machining process parameter optimization method based on long-term and short-term memory, so as to solve the problems in the prior art.
In order to achieve the above object, an embodiment of the present invention provides the following:
a numerical control machining process parameter optimization method based on long and short term memory is characterized by comprising the following steps:
step S1, operating the G code of the numerical control machine tool to obtain the instruction sequence number of the G code, and working task data and state data including the feeding speed;
step S2, the deep neural network forwards propagates and predicts the feeding speed of the nth time of the G code of the mth line of the next state of the current state according to the received state data of the current state
Figure BDA0002155507370000011
Step S3, judging the feeding speed
Figure BDA0002155507370000012
Whether the speed is within the allowable range of the feeding speed, if so, the next step S4 is carried out, otherwise, the step S2 is returned to;
step S4, using the predicted feeding speed of the next state
Figure BDA0002155507370000013
Carrying out nth replacement correction on the feeding speed of the G code of the original mth line, and operating the corrected G code;
step S5, judging whether the processing precision ERR and the processing efficiency are larger than the preset values, if so, executing the next step S6, otherwise, returning to the step S2
Step S6, judging whether the parameters are finished, if so, turning to the next step S7, otherwise, returning to the step S1
And step S7, extracting the optimal parameters.
Preferably, the deep neural network in step S2 is a long-short term memory neural network and is trained in advance.
Preferably, the training method of the deep neural network includes:
step 201, acquiring a displacement increment during program operation of a position control device of a numerical control machine tool, acquiring a feeding speed from a numerical control device, segmenting data of the displacement increment and the feeding speed, and dividing the data into M-segment signals corresponding to the machining processes of M machined workpieces;
step 202, conducting regularization processing on each segment of signal to enable the length of each segment of signal to be consistent, and then sending the regularized displacement increment signal data of each segment into a long-term and short-term memory network for training, wherein the input sequence is X e { X ∈t|Ti＜T＜Ti+ΔIn which xt＝[Δx,Δy,Δz]The increment of X, Y, Z for each axis, T is the G code line number;
step S3 predicts the feed rate using the result of the training of the displacement increment, and outputs Y ═ Yt|Ti＜T＜Ti+ΔIn which yt＝[ΔFx,ΔFy,ΔFz]For the predicted feed speed of the respective axis, use is made of the known actual feed speed yFruit of Chinese wolfberryTo obtain the actual feeding speed yFruit of Chinese wolfberryAnd the predicted feed speed ytThe error value of (2) is minimized by a back propagation algorithm and a random gradient descent method, so that the training of the deep neural network can be finally completed.
Preferably, in the step S3,
the judgment of the feeding speed is the primary filtering of the prediction result, and is not limited to whether the highest feeding speed is exceeded or not;
if the minimum feed speed is lower, the filtering range is also included;
if the prediction is carried out more than two times, the prediction value is more than the maximum feeding speed
Figure BDA0002155507370000021
Or less than a minimum speed
Figure BDA0002155507370000022
Each takes less than the maximum value FmaxSuitable value Fma(ii) a And is greater than FminSuitable value Fmi；
The value of the feed rate may be set in advance or may be set according to conditions.
Preferably, in the step S4, the feeding speed is adjusted
Figure BDA0002155507370000031
The local replacement is preferentially carried out and then the global replacement is carried out.
Preferably, the work task data is a G code moving at a feeding speed F, and the state data is a feeding shaft current, a pulse signal, a position increment and a feeding speed directly obtained from the inside of the numerical control machine.
Preferably, the processing accuracy ERR expression is:
Figure BDA0002155507370000032
wherein R is the difference between the actual trajectory and the commanded trajectory.
The embodiment of the invention has the following advantages:
the method mainly combines the strong perception capability of the neural network to carry out prediction optimization on the parameters, and avoids the uncertainty of the traditional experience; the numerical control program with the optimal parameters can be generated under the condition that the program is in the stable working state of the maximum safe load, so that the quality of the program is improved; the optimal parameters can be extracted and can be used repeatedly, thereby improving the production efficiency.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It should be apparent that the drawings in the following description are merely exemplary, and that other embodiments can be derived from the drawings provided by those of ordinary skill in the art without inventive effort.
FIG. 1 is a schematic flow chart of a method for optimizing processing parameters according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a training process of long-term and short-term memory according to an embodiment of the present invention;
FIG. 3 is a chain structure diagram of a long term memory network according to an embodiment of the present invention;
FIG. 4 is a diagram of the structure of the neural unit of long-short term memory according to an embodiment of the present invention.
Detailed Description
The present invention is described in terms of particular embodiments, other advantages and features of the invention will become apparent to those skilled in the art from the following disclosure, and it is to be understood that the described embodiments are merely exemplary of the invention and that it is not intended to limit the invention to the particular embodiments disclosed. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in FIG. 1, the invention provides a numerical control machining process parameter optimization method based on long-term and short-term memory, which comprises the following specific steps:
step S1, running the numerical control G code to obtain the working task data and state data including the instruction sequence number of the G code and the feeding speed F;
wherein, the working task data is a G code moving at a feeding speed F, and the state data is the current, a pulse signal, a position increment, a feeding speed and the like of a feeding shaft directly acquired from the inside of the numerical control machine tool.
Step S2, the deep neural network forwards propagates and predicts the feed speed of the nth time of the mth line G code of the next state in the state according to the received work task data and state data
Figure BDA0002155507370000041
In which the parameters of the neural network are trained in advance
The deep neural network is a long-term and short-term memory neural network, and the training method of the deep neural network is shown in figure 2 and specifically comprises the following steps:
step 201, acquiring displacement increment of a position control device of a numerical control machine tool during program operation, acquiring a feeding speed from a numerical control device, segmenting data, and dividing the machining process of M machined workpieces into M sections of signals corresponding to the M sections of signals;
step 202, conducting regularization processing on each segment of signal to enable the length of each segment of signal to be consistent, and then sending the regularized displacement increment signal data of each segment into a long-term and short-term memory network for training, wherein the input sequence is X e { X ∈t|Ti＜T＜Ti+ΔIn which xt＝[Δx,Δy,Δz]The increment of X, Y, Z for each axis, T is the G code line number;
in this embodiment, the long-short term memory network (LSTM) is a special form of the Recurrent Neural Network (RNN) (as shown in fig. 3), which solves the problem of reduced attenuation of the RNN in the back propagation process, so that the long-term history information can be used to help the network make decisions, and its neural unit is shown in fig. 4, and a forgetting gate f determines which information in the discarded neurons needs to be discarded; inputting exit i and g to determine to update the preservation information in the cells; the output gate o determines the output information;
ft＝σ(Wfxxt+Wfhht-1)+bf
it＝σ(Wixxt+Wihht-1)+bi
gt＝ψ(Wgxxt+Wghht-1)+bg
ot＝σ(Woxxt+Wohht-1)+bo
St＝gi·it+st-1·ft
ht＝ot·ψ(st)
wherein W is a weight signal, b is an offset value, and htIn the formula, ψ (x) ═ tanh (x) and σ (x) ═ 1/(1+ e) are hidden layers-x)。
Step 203, the feed speed is predicted by the result of the training of the displacement increment, and the output is Y ═ Y { (Y)pr|Ti＜T＜Ti+ΔIn which ypr＝[ΔFx,ΔFy,ΔFz]For the predicted feed speed of the respective axis, use is made of the known actual feed speed ytThe actual feed speed y can be obtainedtAnd the predicted feed speed ypThe error value of (2) is minimized by a random gradient descent method of a back propagation algorithm, and the training can be finally completed.
Specifically, after training by using the processed displacement increment data as the input of a long-short term memory network (LSTM), the network encodes the input data X and decodes the encoded data X during output to obtain a preliminary feed speed predicted value Y, and utilizes the actual feed speed YtAnd the predicted feed speed ypIn order to minimize the difference, the gradient of the neural network is calculated by adopting a random gradient descent method of a back propagation algorithm, the error is smaller than a preset value through multiple calculations, the training of the model is finally completed, and the real-time feeding speed can be predicted in the actual operation of the trained network.
Step S3, adjusting the feeding speed
Figure BDA0002155507370000061
Judging whether the speed is within the allowable range of the feeding speed, if so, turning to S4, otherwise, returning to S2;
for the feed speed
Figure BDA0002155507370000062
Judging whether the feeding speed is judged to be the primary filtering of the prediction result, and not limited to whether the highest feeding speed is exceeded or not;
if the minimum feed speed is lower, the filtering range is also included;
if the prediction is carried out more than two times, the prediction value is more than the maximum feeding speed
Figure BDA0002155507370000063
Or less than a minimum speed
Figure BDA0002155507370000064
Each takes less than the maximum value FmaxSuitable value FmaAnd is greater than FminSuitable value Fmi. The value can be preset or set according to conditions, and if the predicted value is equal to the actual value, the original value is kept unchanged; step S4, using the predicted feeding speed
Figure BDA0002155507370000065
Carrying out nth replacement correction on the feeding speed of the original mth line G code, and operating;
to pair
Figure BDA0002155507370000066
The replacement is carried out, wherein local replacement is preferred, and global replacement is the second replacement;
and step S5, judging whether the machining precision ERR and the machining efficiency are larger than preset values, if so, executing step S6, and otherwise, returning to step S2.
If the machining precision can be obtained by using the difference R between the actual running track and the instruction running track
Figure BDA0002155507370000067
And (6) judging.
Step S6, judging whether the parameters are finished, if so, turning to step S7, otherwise, returning to step S1;
and step S7, extracting the optimal parameters.
The method mainly combines the strong perception capability of the neural network to carry out prediction optimization on the parameters, and avoids the uncertainty of the traditional experience; the numerical control program with the optimal parameters can be generated under the condition that the program is in the stable working state of the maximum safe load, so that the quality of the program is improved; the optimal parameters can be extracted and can be used repeatedly, thereby improving the production efficiency.
Although the invention has been described in detail above with reference to a general description and specific examples, it will be apparent to one skilled in the art that modifications or improvements may be made thereto based on the invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.

Claims (6)

1. A numerical control machining process parameter optimization method based on long and short term memory is characterized by comprising the following steps:
step S1, operating the G code of the numerical control machine tool to obtain the instruction sequence number of the G code, and working task data and state data including the feeding speed;
step S2, the deep neural network forwards propagates and predicts the feeding speed of the nth time of the G code of the mth line of the next state of the current state according to the received state data of the current state
Figure FDA0002930004450000011
The training method of the deep neural network comprises the following steps:
step 201, acquiring a displacement increment during program operation of a position control device of a numerical control machine tool, acquiring a feeding speed from a numerical control device, segmenting data of the displacement increment and the feeding speed, and dividing the data into M-segment signals corresponding to the machining processes of M machined workpieces;
step 202, conducting regularization processing on each segment of signal to make the length of each segment of signal consistent, and then sending the regularized displacement increment signal data of each segment into a long-term and short-term memory networkTraining in the network, wherein the input sequence is X e { X ∈ [ ]t|Ti＜T＜Ti+ΔIn which xt＝[Δx,Δy,Δz]The increment of X, Y, Z for each axis, T is the G code line number;
step S203 predicts the feed rate using the result of the training of the displacement increment, and outputs Y ═ Yt|Ti＜T＜Ti+ΔIn which yt＝[ΔFx,ΔFy,ΔFz]For the predicted feed speed of the respective axis, use is made of the known actual feed speed yFruit of Chinese wolfberryTo obtain the actual feeding speed yFruit of Chinese wolfberryAnd the predicted feed speed ytThe error value of (2) is minimized by a back propagation algorithm and a random gradient descent method, so that the training of the deep neural network can be finally completed;
step S3, judging the feeding speed
Figure FDA0002930004450000012
Whether the speed is within the allowable range of the feeding speed, if so, the next step S4 is carried out, otherwise, the step S2 is returned to;
step S4, using the predicted feeding speed of the next state
Figure FDA0002930004450000013
Carrying out nth replacement correction on the feeding speed of the G code of the original mth line, and operating the corrected G code;
step S5, judging whether the processing precision ERR and the processing efficiency are larger than preset values, if so, executing the next step S6, otherwise, returning to the step S2;
step S6, judging whether the parameters are finished, if so, turning to the next step S7, otherwise, returning to the step S1;
and step S7, extracting the optimal parameters.
2. The method for optimizing the parameters of the NC machining process based on the long-short term memory as claimed in claim 1, wherein the deep neural network in the step S2 is a long-short term memory neural network and is pre-trained.
3. The method for optimizing numerical control machining process parameters based on long-short term memory as claimed in claim 1, wherein in the step S3,
the judgment of the feeding speed is the primary filtering of the prediction result, and is not limited to the judgment of exceeding the highest feeding speed;
if the minimum feed speed is lower, the filtering range is also included;
in predicting the feed speed, if the predicted value is greater than the maximum feed speed
Figure FDA0002930004450000021
More than twice, or the predicted value is less than the minimum speed
Figure FDA0002930004450000022
If the number of times exceeds two times, the predicted value is selected to be less than the maximum value FmaxIs a suitable value of Fma(ii) a Or greater than FminIs a suitable value of Fmi；
The value of the feed rate may be set in advance or may be set according to conditions.
4. The numerical control machining process parameter optimizing method based on long-term and short-term memory as claimed in claim 1, wherein in the step S4, the feeding speed is adjusted
Figure FDA0002930004450000023
The local replacement is preferentially carried out and then the global replacement is carried out.
5. The numerical control machining process parameter optimization method based on the long-term and short-term memory is characterized in that the work task data is a G code of motion at a feeding speed F, and the state data is the current, a pulse signal, a position increment and the feeding speed of a feeding shaft directly acquired from the interior of the numerical control machine.
6. The numerical control machining process parameter optimization method based on the long-term and short-term memory as claimed in claim 1, wherein the machining precision ERR expression is as follows:
Figure FDA0002930004450000024
wherein R is the difference between the actual trajectory and the commanded trajectory.
CN201910716189.7A 2019-08-05 2019-08-05 Numerical control machining process parameter optimization method based on long-term and short-term memory Active CN110442099B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910716189.7A CN110442099B (en) 2019-08-05 2019-08-05 Numerical control machining process parameter optimization method based on long-term and short-term memory

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910716189.7A CN110442099B (en) 2019-08-05 2019-08-05 Numerical control machining process parameter optimization method based on long-term and short-term memory

Publications (2)

Publication Number Publication Date
CN110442099A CN110442099A (en) 2019-11-12
CN110442099B true CN110442099B (en) 2021-05-11

Family

ID=68433150

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910716189.7A Active CN110442099B (en) 2019-08-05 2019-08-05 Numerical control machining process parameter optimization method based on long-term and short-term memory

Country Status (1)

Country Link
CN (1) CN110442099B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113065630B (en) * 2021-03-23 2023-04-07 重庆大学 Technological parameter optimization method for abrasive belt grinding
CN113592064B (en) * 2021-07-05 2024-02-09 中国科学院上海光学精密机械研究所 Ring polishing process parameter prediction method, system, application, terminal and medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63250712A (en) * 1987-04-07 1988-10-18 Minolta Camera Co Ltd Control device for numerical control working machine
CN108932581A (en) * 2018-06-06 2018-12-04 深圳大学 The autonomous cognitive method and system of more physics domain information fusions
CN109711714A (en) * 2018-12-24 2019-05-03 浙江大学 Product quality prediction technique is assembled in manufacture based on shot and long term memory network in parallel

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080255684A1 (en) * 2002-11-18 2008-10-16 Universiti Putra Malaysia Artificial intelligence device and corresponding methods for selecting machinability data
CN104777785B (en) * 2015-03-02 2016-04-20 华中科技大学 A kind of numerical control processing technology dynamic state of parameters optimization method analyzed based on domain of instruction
CN109131452B (en) * 2018-08-14 2021-06-15 西安理工大学 Train state online prediction method based on long-time and short-time memory network
CN109396576B (en) * 2018-09-29 2020-02-04 郑州轻工业学院 Deep learning-based electric spark machining stability and energy consumption state optimization decision system and decision method

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS63250712A (en) * 1987-04-07 1988-10-18 Minolta Camera Co Ltd Control device for numerical control working machine
CN108932581A (en) * 2018-06-06 2018-12-04 深圳大学 The autonomous cognitive method and system of more physics domain information fusions
CN109711714A (en) * 2018-12-24 2019-05-03 浙江大学 Product quality prediction technique is assembled in manufacture based on shot and long term memory network in parallel

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
《Modeling and Optimization of Paper-making Wastewater Treatment Based on Reinforcement Learning》;Zhiwei Zhuang;《2018 37th Chinese Control Conference》;20181231;第8342页-第8346页 *
《数控车床加工工艺流程的优化改进》;吴福昌;《机电工程技术》;20190703(第6期);第34页-第35页，第250页 *

Also Published As

Publication number Publication date
CN110442099A (en) 2019-11-12

Similar Documents

Publication Publication Date Title
JP6680756B2 (en) Control device and machine learning device
JP5969676B1 (en) Machine learning device and machine learning method for optimizing frequency of tool correction of machine tool, and machine tool including the machine learning device
JP6470251B2 (en) Numerical control device and machine learning device
CN110442099B (en) Numerical control machining process parameter optimization method based on long-term and short-term memory
JP6063013B1 (en) Numerical control device with machining condition adjustment function to suppress chatter or tool wear / breakage
CN109283887B (en) Machine learning device, numerical controller, numerical control system, and machine learning method
JP6457563B2 (en) Numerical control device and machine learning device
JP6348098B2 (en) Wire EDM machine simulation device with core welding position determination function using machine learning
US11640557B2 (en) Machine learning device, numerical control system, and machine learning method
US11119464B2 (en) Controller and machine learning device
EP3213161A1 (en) Method for optimizing the productivity of a machining process of a cnc machine
CN108303952B (en) Speed curve planning method suitable for small line segment of numerical control device cutter
US9921567B2 (en) High speed smooth tool path
US11262723B2 (en) Machining path generation device and numerical control device
CN107037781A (en) Process time prediction meanss
JP2019020959A (en) Control device and learning device
CN106970589A (en) A kind of feed rate relaxation method for reducing Multi-axis Machining profile errors
CN106325220A (en) Numerical controller performing 3-dimensional interference check corresponding to feedrate change
TW202001460A (en) Smart adjustment system and method thereof
JP6412086B2 (en) Numerical controller
CN107491036B (en) Machine tool machining energy consumption control method and machine tool
JP6940474B2 (en) Machine Tools
CN113449428B (en) Cutter point optimization method adopting multi-stage correction and coupling thinning algorithm
Moreira et al. Supervision control for quality assurance in milling processes
Viharos et al. Integrated Experimental design and parameter optimization under uncertain process circumstances

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20191112

Assignee: Chongqing Fangding Technology Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002285

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240228

Application publication date: 20191112

Assignee: Chongqing Qiluo Machinery Manufacturing Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002283

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240228

Application publication date: 20191112

Assignee: CHONGQING QILUO FLUID EQUIPMENT Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002282

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240228

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20191112

Assignee: Chongqing Yiquan Small and Medium Enterprise Service Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002570

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240307

Application publication date: 20191112

Assignee: Youzhengyun (Chongqing) Technology Development Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002569

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240307

Application publication date: 20191112

Assignee: Yuao Holdings Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002568

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240307

Application publication date: 20191112

Assignee: Chongqing Qinlang Technology Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002576

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240307

Application publication date: 20191112

Assignee: Chongqing Shuaicheng Network Technology Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002572

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240307

Application publication date: 20191112

Assignee: Bainuo Zhongcheng (Chongqing) Electronic Technology Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980002571

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240307

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20191112

Assignee: Chongqing Baiyi medical supplies Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980003000

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240319

EE01 Entry into force of recordation of patent licensing contract
EE01 Entry into force of recordation of patent licensing contract

Application publication date: 20191112

Assignee: Chongqing Luqian Technology Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980003374

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240325

Application publication date: 20191112

Assignee: Chongqing Difeida Technology Co.,Ltd.

Assignor: XIANGTAN University

Contract record no.: X2024980003371

Denomination of invention: A Method for Optimizing CNC Machining Process Parameters Based on Long Short Term Memory

Granted publication date: 20210511

License type: Common License

Record date: 20240325